diff options
Diffstat (limited to 'drivers/nvme/host/tcp.c')
| -rw-r--r-- | drivers/nvme/host/tcp.c | 83 |
1 files changed, 54 insertions, 29 deletions
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 62fbaecdc960..c0c33320fe65 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -464,6 +464,7 @@ static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl) if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) return; + dev_warn(ctrl->device, "starting error recovery\n"); queue_work(nvme_reset_wq, &to_tcp_ctrl(ctrl)->err_work); } @@ -481,7 +482,7 @@ static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue, return -EINVAL; } - if (!nvme_end_request(rq, cqe->status, cqe->result)) + if (!nvme_try_complete_req(rq, cqe->status, cqe->result)) nvme_complete_rq(rq); queue->nr_cqe++; @@ -672,7 +673,7 @@ static inline void nvme_tcp_end_request(struct request *rq, u16 status) { union nvme_result res = {}; - if (!nvme_end_request(rq, cpu_to_le16(status << 1), res)) + if (!nvme_try_complete_req(rq, cpu_to_le16(status << 1), res)) nvme_complete_rq(rq); } @@ -866,7 +867,6 @@ static void nvme_tcp_state_change(struct sock *sk) case TCP_LAST_ACK: case TCP_FIN_WAIT1: case TCP_FIN_WAIT2: - /* fallthrough */ nvme_tcp_error_recovery(&queue->ctrl->ctrl); break; default: @@ -912,12 +912,11 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req) else flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST; - /* can't zcopy slab pages */ - if (unlikely(PageSlab(page))) { - ret = sock_no_sendpage(queue->sock, page, offset, len, + if (sendpage_ok(page)) { + ret = kernel_sendpage(queue->sock, page, offset, len, flags); } else { - ret = kernel_sendpage(queue->sock, page, offset, len, + ret = sock_no_sendpage(queue->sock, page, offset, len, flags); } if (ret <= 0) @@ -1527,7 +1526,6 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid) if (!test_and_clear_bit(NVME_TCP_Q_LIVE, &queue->flags)) return; - __nvme_tcp_stop_queue(queue); } @@ -1596,6 +1594,7 @@ static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl, static void nvme_tcp_free_admin_queue(struct nvme_ctrl *ctrl) { if (to_tcp_ctrl(ctrl)->async_req.pdu) { + cancel_work_sync(&ctrl->async_event_work); nvme_tcp_free_async_req(to_tcp_ctrl(ctrl)); to_tcp_ctrl(ctrl)->async_req.pdu = NULL; } @@ -1782,7 +1781,15 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) if (!new) { nvme_start_queues(ctrl); - nvme_wait_freeze(ctrl); + if (!nvme_wait_freeze_timeout(ctrl, NVME_IO_TIMEOUT)) { + /* + * If we timed out waiting for freeze we are likely to + * be stuck. Fail the controller initialization just + * to be safe. + */ + ret = -ENODEV; + goto out_wait_freeze_timed_out; + } blk_mq_update_nr_hw_queues(ctrl->tagset, ctrl->queue_count - 1); nvme_unfreeze(ctrl); @@ -1790,6 +1797,9 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) return 0; +out_wait_freeze_timed_out: + nvme_stop_queues(ctrl); + nvme_tcp_stop_io_queues(ctrl); out_cleanup_connect_q: if (new) blk_cleanup_queue(ctrl->connect_q); @@ -1876,6 +1886,7 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl, bool remove) { blk_mq_quiesce_queue(ctrl->admin_q); + blk_sync_queue(ctrl->admin_q); nvme_tcp_stop_queue(ctrl, 0); if (ctrl->admin_tagset) { blk_mq_tagset_busy_iter(ctrl->admin_tagset, @@ -1892,8 +1903,10 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl, { if (ctrl->queue_count <= 1) return; + blk_mq_quiesce_queue(ctrl->admin_q); nvme_start_freeze(ctrl); nvme_stop_queues(ctrl); + nvme_sync_io_queues(ctrl); nvme_tcp_stop_io_queues(ctrl); if (ctrl->tagset) { blk_mq_tagset_busy_iter(ctrl->tagset, @@ -2149,40 +2162,52 @@ static void nvme_tcp_submit_async_event(struct nvme_ctrl *arg) nvme_tcp_queue_request(&ctrl->async_req, true, true); } +static void nvme_tcp_complete_timed_out(struct request *rq) +{ + struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); + struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl; + + nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue)); + if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) { + nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD; + blk_mq_complete_request(rq); + } +} + static enum blk_eh_timer_return nvme_tcp_timeout(struct request *rq, bool reserved) { struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); - struct nvme_tcp_ctrl *ctrl = req->queue->ctrl; + struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl; struct nvme_tcp_cmd_pdu *pdu = req->pdu; - /* - * Restart the timer if a controller reset is already scheduled. Any - * timed out commands would be handled before entering the connecting - * state. - */ - if (ctrl->ctrl.state == NVME_CTRL_RESETTING) - return BLK_EH_RESET_TIMER; - - dev_warn(ctrl->ctrl.device, + dev_warn(ctrl->device, "queue %d: timeout request %#x type %d\n", nvme_tcp_queue_id(req->queue), rq->tag, pdu->hdr.type); - if (ctrl->ctrl.state != NVME_CTRL_LIVE) { + if (ctrl->state != NVME_CTRL_LIVE) { /* - * Teardown immediately if controller times out while starting - * or we are already started error recovery. all outstanding - * requests are completed on shutdown, so we return BLK_EH_DONE. + * If we are resetting, connecting or deleting we should + * complete immediately because we may block controller + * teardown or setup sequence + * - ctrl disable/shutdown fabrics requests + * - connect requests + * - initialization admin requests + * - I/O requests that entered after unquiescing and + * the controller stopped responding + * + * All other requests should be cancelled by the error + * recovery work, so it's fine that we fail it here. */ - flush_work(&ctrl->err_work); - nvme_tcp_teardown_io_queues(&ctrl->ctrl, false); - nvme_tcp_teardown_admin_queue(&ctrl->ctrl, false); + nvme_tcp_complete_timed_out(rq); return BLK_EH_DONE; } - dev_warn(ctrl->ctrl.device, "starting error recovery\n"); - nvme_tcp_error_recovery(&ctrl->ctrl); - + /* + * LIVE state should trigger the normal error recovery which will + * handle completing this request. + */ + nvme_tcp_error_recovery(ctrl); return BLK_EH_RESET_TIMER; } |